ChartQA-X: Generating Explanations for Visual Chart Reasoning
This work addresses the problem of improving comprehension and trust in AI-generated chart explanations for data-driven decision-making, representing a domain-specific advancement.
The authors tackled the challenge of generating detailed explanations alongside answering questions about charts by creating ChartQA-X, a dataset of 30,299 chart samples with questions, answers, and explanations, and showed that model-generated explanations surpass human-written ones in accuracy and logic, with fine-tuned models achieving gains of up to 24.57 points in explanation quality and 18.96 percentage points in question-answering accuracy.
The ability to explain complex information from chart images is vital for effective data-driven decision-making. In this work, we address the challenge of generating detailed explanations alongside answering questions about charts. We present ChartQA-X, a comprehensive dataset comprising 30,299 chart samples across four chart types, each paired with contextually relevant questions, answers, and explanations. Explanations are generated and selected based on metrics such as faithfulness, informativeness, coherence, and perplexity. Our human evaluation with 245 participants shows that model-generated explanations in ChartQA-X surpass human-written explanations in accuracy and logic and are comparable in terms of clarity and overall quality. Moreover, models fine-tuned on ChartQA-X show substantial improvements across various metrics, including absolute gains of up to 24.57 points in explanation quality, 18.96 percentage points in question-answering accuracy, and 14.75 percentage points on unseen benchmarks for the same task. By integrating explanatory narratives with answers, our approach enables agents to convey complex visual information more effectively, improving comprehension and greater trust in the generated responses.